Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2432 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0530. Min Act: -0.1700

Data Index: 5914469 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0873. Min Act: -0.1700

Data Index: 8394730 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0695. Min Act: -0.1700

Data Index: 7356646 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0809. Min Act: -0.1700

Data Index: 1867523 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0814. Min Act: -0.1700

Data Index: 6821593 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0828. Min Act: -0.1700

Data Index: 295386 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0216. Min Act: -0.1700

Data Index: 8640685 (Open Web Text)

Max Activating Token Index: 879

Text #7

Max Range: 4.0873. Min Range: -4.0873

Max Act: 3.9961. Min Act: -0.1700

Data Index: 4964371 (Open Web Text)

Max Activating Token Index: 614

Text #8

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0434. Min Act: -0.1700

Data Index: 4779539 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0463. Min Act: -0.1700

Data Index: 1884427 (Open Web Text)

Max Activating Token Index: 451

Text #10

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0482. Min Act: -0.1700

Data Index: 6124669 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0618. Min Act: -0.1700

Data Index: 1664741 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0533. Min Act: -0.1700

Data Index: 12 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0096. Min Act: -0.1700

Data Index: 2272885 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0079. Min Act: -0.1700

Data Index: 7964793 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 4.0873. Min Range: -4.0873

Max Act: 3.9817. Min Act: -0.1700

Data Index: 5239455 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0014. Min Act: -0.1700

Data Index: 8091541 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0274. Min Act: -0.1700

Data Index: 3151307 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0102. Min Act: -0.1700

Data Index: 5693135 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 4.0873. Min Range: -4.0873

Max Act: 4.0144. Min Act: -0.1700

Data Index: 634918 (Open Web Text)

Max Activating Token Index: 896